© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58474
    Prev
    Next
    INDEX
    Explanations

    internet and online discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīī
    -0.11
     patron
    -0.09
    éĺħ读åħ¨æĸĩ
    -0.09
    çľĭä¸įè§ģ
    -0.09
    oes
    -0.08
    Newsletter
    -0.08
    åĨ¬å¥¥
    -0.08
    èµ³
    -0.08
    ä¸Ģ度
    -0.08
    ä¹Łå¸ĮæľĽ
    -0.08
    POSITIVE LOGITS
    åľ¨ç½ijä¸Ĭ
    0.16
    ç½ijä¸Ĭ
    0.16
    åľ¨ç½ij绾ä¸Ĭ
    0.15
     internet
    0.14
     инÑĤеÑĢнеÑĤ
    0.13
    论åĿĽ
    0.13
    internet
    0.13
    æĶ»çķ¥
    0.13
    äºĴèģĶç½ij
    0.12
     online
    0.12
    Activations Density 0.270%

    No Known Activations